Approximation of level continuous fuzzy-valued functions by multilayer regular fuzzy neural networks

Authors:
Huan Huang;Congxin Wu
Affiliations:
Department of Mathematics, Jimei University, Xiamen 361021, China;Department of Mathematics, Harbin Institute of Technology, Harbin 150001, China
Venue:
Mathematical and Computer Modelling: An International Journal
Year:
2009

Citing 9
Cited 2

Approximation capabilities of multilayer feedforward networks

Neural Networks
Approximation and radial-basis-function networks

Neural Computation
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Can fuzzy neural nets approximate continuous fuzzy functions?

Fuzzy Sets and Systems
Analyses of regular fuzzy neural networks for approximation capabilities

Fuzzy Sets and Systems
Universal approximations of continuous fuzzy-valued functions by multi-layer fuzzy neural networks

Fuzzy Sets and Systems
Fuzzy nonlinear regression with fuzzified radial basis function network

IEEE Transactions on Fuzzy Systems
Universal approximation bounds for superpositions of a sigmoidal function

IEEE Transactions on Information Theory
Approximation capability in C(R¯n) by multilayer feedforward networks and related problems

IEEE Transactions on Neural Networks

Interval type-2 fuzzy neural networks version of the Stone-Weierstrass theorem

Neurocomputing
Approximation of fuzzy functions by regular fuzzy neural networks

Fuzzy Sets and Systems

Quantified Score

Hi-index	0.98

Visualization

Abstract

This paper proves the capability of approximation by four-layer regular fuzzy neural networks on the set of all level continuous fuzzy-valued functions according to level convergence. A numerical example is given to illustrate the results.